cs848-w2024

Weekly Schedule

Note that all of the readings are accessible from the original repositories I have linked to if you access them from the University (or use VPN ihrnto SCS if you are accessing from home).

Week Date Topic Speaker Readings Slides
1 1/11 Introduction to Disaggregated & Heterogeneous Platforms M. Tamer Özsu * R. Wang et al., The Case for Shared-Memory Databases with RDMA-Enabled Memory Disaggregation, Proc. VLDB Endowment, 2022.
* I. Blagodurov et al., The time is ripe for disaggregated systems. Computer Architecture Today – ACM SIGARCH Blog, 2021.
* S. Ghandeharizadeh et al., Disaggregated database management systems. In Performance Evaluation and Benchmarking, 2023.
Slides
2 1/18 Introduction to Graph Processing M. Tamer Özsu * M. Besta et al., Demystifying Graph Databases: Analysis and Taxonomy of Data Organization, System Designs, and Graph Queries, ACM Comput. Surv. 56(2): 31:1-31:40, 2024.
* M.T. Özsu and P. Valduriez, Big Data Processing. In Principles of Distributed Database Systems. Springer, 2022. (Focus on Section 10.4)
* M.T. Özsu and P. Valduriez, Big Data Processing. In Principles of Distributed Database Systems. Springer, 2022. (Focus on Section 12.6)
Slides
3 1/25 Networking infrastructure Samer Al-Kiswany
Ahmed Alquraan
* R. Recio, A Tutorial of the RDMA Model, HPC Wire, 2006.
* InfiniBand Trade Organization, Enabling the Modern Data Center – RDMA for the Enterprise, 2019.
* A. Lerner et al., Databases on modern networks: A decade of research that now comes into practice. Proc. VLDB Endowment, 16(12):3894–3897, 2023.
* D. Gouk et al., Direct access, High-Performance memory disaggregation with DirectCXL. In Proc. USENIX 2022 Annual Technical Conf., pages 287–294, 2022.
 
4 2/1 Storage disaggregation Lasantha Fernando


Chanaka L. Lokupothagamage
* A. Verbitski et al., Amazon Aurora: Design Considerations for High Throughput Cloud-Native Relational Databases, In Proc. ACM SIGMOD Int. Conf. Management of Data, pages 1041–1052, 2017.
* P. Antonopoulos, et al., Socrates: The New SQL Server in the Cloud, In Proc. ACM SIGMOD Int. Conf. Management of Data, pages 1743–1756, 2019.
Lasantha Slides


Chanaka Slides
5 2/8 Storage disaggregation Amin Setayesh


Moni Haque
* W. Cao et al., PolarFS: An Ultra-low Latency and Failure Resilient Distributed File System for Shared Storage Cloud Database, Proc. VLDB Endowment, 11(12): 1849-1962, 2018.
* M. Vuppalapati et al., Building An Elastic Query Engine on Disaggregated Storage, In Proc. 17th USENIX Symp. on Networked Systems Design & Implementation, pages 449-462, 2020.
Amin Slides


Moni Slides
6 2/15 Storage/Memory disaggregation Arman Davoodi


Guanqi Huang
* A. Agiwal et al., Napa: Powering Scalable Data Warehousing with Robust Query Performance at Google, 14(12): 2986-2998, 2021.
* Y. Shan et al., LegoOS: A Disseminated, Distributed OS for Hardware Resource Disaggregation, In Proc. 14th USENIX Symp. on Operating System Design and Implementation, pages 69-87, 2018.
Arman Slides


Guanqi Slides
7 2/22 No class – Reading week      
8 2/29 No class – I have a conflict      
9 3/7 Memory disaggregation Joseph Boulis


Brian Song
* Y. Zhang et al., Towards Cost-Effective and Elastic Cloud Database Deployment via Memory Disaggregation, Proc. VLDB Endowment, 14(10): 1900 - 1912, 2021.
* Wei Cao et al., PolarDB Serverless: A Cloud Native Database for Disaggregated Data Centers, In Proc. ACM SIGMOD Int. Conf. Management of Data, pages 2477–2489, 2021.
Joseph Slides


Brian Slides
10 3/12 Hardware accelerators Tilmann Rabl, Hasso Plattner Institute












Xiangyao Yu, Uni. Wisconsin-Madison
* C. Lutz et al., Pump Up the Volume: Processing Large Data on GPUs with Fast Interconnects, In Proc. ACM SIGMOD Int. Conf. Management of Data, pages 1633–1649, 2020. (This is the paper to review.)
* T. Maltenberger et al, Evaluating Multi-GPU Sorting with Modern Interconnects, In Proc. ACM SIGMOD International Conference on Management of Data, , pages 1795–1809, 2022.


* B. Yogatama et al, Orchestrating Data Placement and Query Execution in Heterogeneous CPU-GPU DBMS, Proc. VLDB Endowment_, 15(11): 2491-2503, 2022. (This is the paper to review.)
A. Shanbhag et al, A Study of the Fundamental Performance Characteristics of GPUs and CPUs for Database Analytics, In Proc. ACM SIGMOD Int. Conf. Management of Data, pages 1617–1632, 2020.
A. Shanbhag et al, Tile-based Lightweight Integer Compression in GPU, In Proc. ACM SIGMOD Int. Conf. Management of Data, pages 1390–1403, 2022.
Tilmann Slides
Tilmann video












Xiangyao Slides
Xiangyao video
11 3/21 Hardware accelerators Gustavo Alonso, ETH Zürich









Wolfgang Lehner & Alexander Krause, TU Dresden
* D. Korilija et al, Farview: Disaggregated Memory with Operator Off-loading for Database Engines, In Proc. 12th Conf. on Innovative Data Syst. Research, 2022. (This is the paper to review)
* Woods et al, Ibex - An Intelligent Storage Engine with Support for Advanced SQL Off-loading, Proc. VLDB Endow, 7(11): 963-974, 2014.



* J. Pietrzyk et al., Program your (custom) SIMD instruction set on FPGA in C++, In Proc. 12th Conf. on Innovative Data Syst. Research, 2024.
Gustavo Slides








Wolfgang/Alexander Slides
12 3/28 Memory disaggregation Sairaj Voruganti






Philip Bernstein, Microsoft Research
* Q. Zhang et al., Understanding the Effect of Data Center Resource Disaggregation on Production DBMSs, Proc. VLDB Endowment, 13(9): 1568-1581, 2020.


* Q. Zhang et al., Redy: Remote Dynamic Memory Cache, Proc. VLDB Endowment, 15(4): 766 - 779, 2022. (This is the paper to review)
* Q. Zhang et al., CompuCache: Remote Computable Caching using Spot VMs, In Proc. Conference on Innovative Data Systems Research, 2022
Sairaj Slides







Phil Slides
Phil Video
13 4/4 Project presentations Arman Davoodi & Emanuel Haque

Amin Setayesh & Sairaj Voruganti

Lasantha Fernando & Chanaka L. Lokupothagamage

Joseph Boulis, Brian Song & Guanqi Huang
Triangle Listing for graphs stored on disaggregated memory


Disaggregating Graph-based Vector Indexes


Data Stream Processing on FaaS with Memory Disaggregation


Elastic Memory Disaggregated System Architecture for Dynamic Workloads
Slides



Slides



Slides



Slides